DEV Community

Михаил profile picture

Михаил

404 bio not found

Joined Joined on  twitter website
Coding-Agent Memory as a Dependency: AI Agent Memory Audit

Coding-Agent Memory as a Dependency: AI Agent Memory Audit

Comments
1 min read
Testing FROST-SOP: AI Agent Orchestration, Retries and Event Auditing

Testing FROST-SOP: AI Agent Orchestration, Retries and Event Auditing

Comments
2 min read
Build and Test an MCP Server from Scratch

Build and Test an MCP Server from Scratch

Comments
14 min read
LLM Function Calling: Comparing Schemas and Tool Selection Across Providers

LLM Function Calling: Comparing Schemas and Tool Selection Across Providers

Comments
16 min read
Safe First-Time Claude Code Setup in VS Code

Safe First-Time Claude Code Setup in VS Code

Comments
14 min read
How to Audit Hidden Reminders and Context Usage in Claude Code Logs

How to Audit Hidden Reminders and Context Usage in Claude Code Logs

Comments
20 min read
How to Turn Trip Photos and Metadata into a Self-Contained HTML Story

How to Turn Trip Photos and Metadata into a Self-Contained HTML Story

Comments
18 min read
Testing Solar Open 2 on Agent Workloads and Long Context

Testing Solar Open 2 on Agent Workloads and Long Context

Comments
14 min read
Cutting agent costs with trace-based model routing

Cutting agent costs with trace-based model routing

Comments
18 min read
Testing Rule and Memory Inheritance Between AI Agents in FROST

Testing Rule and Memory Inheritance Between AI Agents in FROST

Comments
16 min read
How Graph Serialization Format Affects GraphRAG Cost and Accuracy

How Graph Serialization Format Affects GraphRAG Cost and Accuracy

Comments
17 min read
Testing an AI Agent When Requirements Change Mid-Conversation

Testing an AI Agent When Requirements Change Mid-Conversation

Comments
16 min read
How Memory Changes a Visual Agent: A Reproducible Pokémon FireRed Test

How Memory Changes a Visual Agent: A Reproducible Pokémon FireRed Test

Comments
15 min read
How to Limit the Damage from an AI Agent Error: A Practical Authority Test

How to Limit the Damage from an AI Agent Error: A Practical Authority Test

Comments
13 min read
SEO Tools in Claude Code: Comparing Hosted and Local MCP

SEO Tools in Claude Code: Comparing Hosted and Local MCP

Comments
15 min read
Coordinating Two Coding Agents with Git Refs and a CRDT

Coordinating Two Coding Agents with Git Refs and a CRDT

Comments
18 min read
Testing Local Prompt-Injection Protection with InjectionShield

Testing Local Prompt-Injection Protection with InjectionShield

Comments
16 min read
Testing Browser Harness: Can an Agent Extend Browser Automation by Itself?

Testing Browser Harness: Can an Agent Extend Browser Automation by Itself?

Comments
13 min read
Run Hermes Fully Locally with QVAC

Run Hermes Fully Locally with QVAC

Comments
17 min read
LobsterAI in Practice: Testing a Local Agent for Documents, Spreadsheets, and the Browser

LobsterAI in Practice: Testing a Local Agent for Documents, Spreadsheets, and the Browser

Comments
20 min read
One Console for Coding Agents: Testing BossConsole

One Console for Coding Agents: Testing BossConsole

Comments
16 min read
Skills for a Coding Agent: Measuring Their Value on a Real Task

Skills for a Coding Agent: Measuring Their Value on a Real Task

Comments
17 min read
Testing AI Guardrails: PII Leaks, Prompt Injection, and Unsafe Responses

Testing AI Guardrails: PII Leaks, Prompt Injection, and Unsafe Responses

Comments
16 min read
Background AI Agent with Remote MCP on the Gemini API

Background AI Agent with Remote MCP on the Gemini API

Comments
20 min read
How to Search by Image: Comparing Google Images, Lens, Multisearch, and AI Mode

How to Search by Image: Comparing Google Images, Lens, Multisearch, and AI Mode

Comments
16 min read
Gemini Omni in Google Vids: Generate and Edit One Clip Step by Step

Gemini Omni in Google Vids: Generate and Edit One Clip Step by Step

Comments
13 min read
Connected Apps in Google Search: Testing Three Practical Scenarios

Connected Apps in Google Search: Testing Three Practical Scenarios

Comments
17 min read
How to Test an AI Agent Sandbox for Data Leaks and Network-Restriction Bypasses

How to Test an AI Agent Sandbox for Data Leaks and Network-Restriction Bypasses

Comments
25 min read
Building a Regression Test Suite for an LLM Application

Building a Regression Test Suite for an LLM Application

Comments
16 min read
LLM Judge Under Test: Direct Scoring vs Pairwise Comparison

LLM Judge Under Test: Direct Scoring vs Pairwise Comparison

Comments
16 min read
Testing an AI agent governance boundary with AgentGovBench

Testing an AI agent governance boundary with AgentGovBench

Comments
18 min read
Langfuse vs Phoenix vs Opik: comparing three AI agent observability tools

Langfuse vs Phoenix vs Opik: comparing three AI agent observability tools

Comments
19 min read
Hidden Prompt Injection: Hacking a Browser Agent and Testing Its Defenses

Hidden Prompt Injection: Hacking a Browser Agent and Testing Its Defenses

1
Comments
18 min read
Protecting AI Agent Tools with the Doberman MCP Proxy

Protecting AI Agent Tools with the Doberman MCP Proxy

Comments
18 min read
Controlling AI Agents in deco Studio: Tools, Permissions, and Cost

Controlling AI Agents in deco Studio: Tools, Permissions, and Cost

Comments
22 min read
waoowaoo AI video pipeline: from text to a voiced video

waoowaoo AI video pipeline: from text to a voiced video

Comments
13 min read
Local RAG in Dify: Build a Workflow and Test Answer Quality

Local RAG in Dify: Build a Workflow and Test Answer Quality

Comments
17 min read
How We Added Confirmation Before an Agent Sends a Message

How We Added Confirmation Before an Agent Sends a Message

Comments
6 min read
How We Built an Autonomous AI Article Publication Pipeline

How We Built an Autonomous AI Article Publication Pipeline

Comments
2 min read
How We Are Building an AI System That Improves Itself

How We Are Building an AI System That Improves Itself

Comments
2 min read
loading...